© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36462
    Prev
    Next
    INDEX
    Explanations

    as many as possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anness
    -0.09
    ä»ģ
    -0.08
    à¹ģà¸Ĺ
    -0.08
    edo
    -0.08
    çĻ¾äº¿
    -0.08
    ness
    -0.08
    hurst
    -0.08
     ë°Ķë¡ľ
    -0.08
    ä»ĸä¹Ł
    -0.08
    ç²ķ
    -0.08
    POSITIVE LOGITS
    обоÑĢоÑĤ
    0.09
    akening
    0.09
    æģ£
    0.09
    ä¸įä»ħèĥ½
    0.09
    ually
    0.09
    åľ¨è¿ĩ渡
    0.08
    åĽŀåIJĪ
    0.08
    bundles
    0.08
    课åłĤ
    0.08
    .Axis
    0.08
    Activations Density 0.038%

    No Known Activations